Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2757 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1120409 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 107954 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0016. Min Act: -0.0003

Data Index: 202037 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1169241 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 451015 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1118596 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1031773 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 943152 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1187654 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1049731 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 631600 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 499520 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0013. Min Act: -0.0003

Data Index: 947395 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0015. Min Act: -0.0003

Data Index: 426654 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 151689 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 586537 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 564791 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 1084241 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 543904 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0016. Min Range: -0.0016

Max Act: 0.0014. Min Act: -0.0003

Data Index: 620732 (C4 (Web Text))

Max Activating Token Index: 763